🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

Connect Your Agents And Harnesses With Any Provider 🦚

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.

Latitude is the open-source ai monitoring platform.

AI observability platform for production LLM and agent systems.

The open-source workspace for building and running AI agents. Build agents through chat, share them with your team, and run background agents on schedules or app events.

Agent Skills as a Memory Layer

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

TraceRoot - open-source observability and self-healing layer for AI agents. YC S25

AI-native OpenTelemetry APM with multi-agent root-cause analysis across traces, metrics, and service topology

React components for visualizing traces from AI agents

Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.

Build, Improve Performance, and Productionize your AI Application

Open-source AI gateway for local agent clients: publish fusion-style multi-model workflows as OpenAI/Claude-compatible virtual models with traces, tokens, latency, and cost visibility.

Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.